Machine learning algorithms for predicting outcomes after prostate brachytherapy

Research Project

Project/Area Number	18K07644
Research Category	Grant-in-Aid for Scientific Research (C)
Allocation Type	Multi-year Fund
Section	一般
Review Section	Basic Section 52040:Radiological sciences-related
Research Institution	Keio University
Principal Investigator	Shiraishi Yutaka 慶應義塾大学, 医学部(信濃町), 講師 (00445339)
Project Period (FY)	2018-04-01 – 2021-03-31
Project Status	Completed (Fiscal Year 2020)
Budget Amount *help	¥3,770,000 (Direct Cost: ¥2,900,000、Indirect Cost: ¥870,000) Fiscal Year 2020: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000) Fiscal Year 2019: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000) Fiscal Year 2018: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Keywords	放射線治療 / 小線源治療 / 前立腺癌 / 機械学習 / ニューラルネットワーク
Outline of Final Research Achievements	Machine learning classification algorithms for prediction of treatment response are becoming more popular in radiotherapy literature. The purpose of this study is to estimate their discriminative performance for outcome prediction after prostate permanent brachytherapy. Machine learning algorithms yield higher discriminative　performance in toxicity prediction after permanent prostate brachytherapy than single dosimetric parameter. Our results also show that machine learning algorithms can predict clinical recurrence after prostate brachytherapy.
Academic Significance and Societal Importance of the Research Achievements	本研究で構築したモデルを活用し、前立腺癌小線源治療後の有害事象出現や再発リスクの高い症例をスクリーニングできる可能性が示唆された。特に、臨床的再発部位を予測することで、再発予防に適した後治療（例えば骨盤リンパ節転移の可能性が高い症例には骨盤領域に対する予防照射を行うなど）を検討できる。治療後の有害事象や再発予防につなげることで、個人のQOL向上が期待されるだけでなく、社会全体としての医療費の削減にも寄与できる可能性がある。